© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 126822
    Prev
    Next
    INDEX
    Explanations

    terms related to vehicle specifications and towing capabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æķ
    -0.08
     Laud
    -0.08
    teÅŁ
    -0.07
    íħĶ
    -0.07
    Äı
    -0.07
    uelles
    -0.07
    943
    -0.06
    ampaign
    -0.06
    698
    -0.06
    yar
    -0.06
    POSITIVE LOGITS
     trailer
    0.10
     trailers
    0.09
    pull
    0.09
     Trailer
    0.09
     pulling
    0.08
     pul
    0.08
     pull
    0.08
    .pull
    0.08
     Pul
    0.08
    _PULL
    0.07
    Activations Density 0.020%

    No Known Activations